Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +11 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|startoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
| 3 |
+
size 1033105
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|startoftext|>",
|
| 3 |
+
"clean_up_tokenization_spaces": false,
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"legacy": true,
|
| 6 |
+
"model_max_length": 4096,
|
| 7 |
+
"pad_token": "<unk>",
|
| 8 |
+
"sp_model_kwargs": {},
|
| 9 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|